Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8015a5b0b59e6d48c0885bba8a647fd2a66786c3787f3ffa18068d637c362dd1
+oid sha256:e11e36a0175b6c82026fe424feb779839be4a0005eb40982fb6b609bb0a3cf81
 size 267832560

run-8/checkpoint-1069/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

run-8/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11e36a0175b6c82026fe424feb779839be4a0005eb40982fb6b609bb0a3cf81
+size 267832560

run-8/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d4d4c8be1af8494ccaa220d638ef882e6533e4ae42eafc895d571912c5d4dd
+size 535727290

run-8/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00b1b7d0cc08031f6a4740ab2e7a24d8967d288d9c7299f21e3d13561d9dded
+size 14308

run-8/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0501e2e73ee9e594baa38bc71ba567695a51ac1576dea6a6aabf83a92ad477
+size 1064

run-8/checkpoint-1069/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-1069/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-1069/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.44113488112476795,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.7455697746568986e-05,
+      "loss": 0.5576,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.3294255615347282e-06,
+      "loss": 0.4954,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.49697768688201904,
+      "eval_matthews_correlation": 0.44113488112476795,
+      "eval_runtime": 0.5275,
+      "eval_samples_per_second": 1977.286,
+      "eval_steps_per_second": 125.121,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1069,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 42054776917848.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.158196993160325e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 21
+  }
+}

run-8/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cab62856ac36c605ce96f4f4ce1747a15722931bff01fac2effe42b7d4f20c2
+size 4664

runs/Jan08_03-19-08_fe6f5592002e/events.out.tfevents.1704686336.fe6f5592002e.4919.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3973bde223efef99c889bfe872d60a3e70643ca2c96bb9669318a04b428fdd29
+size 5192

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f94afec3137acb97928db163d93043fac47e11daafef46a80ab44daa849b5b3
+oid sha256:9cab62856ac36c605ce96f4f4ce1747a15722931bff01fac2effe42b7d4f20c2
 size 4664